Skip to content

cloud-kernel
cloud-kernel

openanolis / cloud-kernel
1 年多 前同步成功

通知 163
Star 36
Fork 7
cloud-kernel
cloud-kernel
切换分支/标签
  1. 01 9月, 2009 1 次提交
  3. 31 8月, 2009 1 次提交
  5. 29 8月, 2009 1 次提交
  7. 14 8月, 2009 1 次提交
  9. 09 7月, 2009 1 次提交
  11. 06 7月, 2009 3 次提交
  13. 17 6月, 2009 1 次提交
  15. 13 6月, 2009 2 次提交
  17. 29 5月, 2009 1 次提交
  19. 25 5月, 2009 1 次提交
  21. 24 5月, 2009 1 次提交
  23. 19 5月, 2009 1 次提交
    • E
      net: release dst entry in dev_hard_start_xmit() · 93f154b5
      由 Eric Dumazet 提交于 
      One point of contention in high network loads is the dst_release() performed
when a transmited skb is freed. This is because NIC tx completion calls
dev_kree_skb() long after original call to dev_queue_xmit(skb).

CPU cache is cold and the atomic op in dst_release() stalls. On SMP, this is
quite visible if one CPU is 100% handling softirqs for a network device,
since dst_clone() is done by other cpus, involving cache line ping pongs.

It seems right place to release dst is in dev_hard_start_xmit(), for most
devices but ones that are virtual, and some exceptions.

David Miller suggested to define a new device flag, set in alloc_netdev_mq()
(so that most devices set it at init time), and carefuly unset in devices
which dont want a NULL skb->dst in their ndo_start_xmit().

List of devices that must clear this flag is :

- loopback device, because it calls netif_rx() and quoting Patrick :
    "ip_route_input() doesn't accept loopback addresses, so loopback packets
     already need to have a dst_entry attached."
- appletalk/ipddp.c : needs skb->dst in its xmit function

- And all devices that call again dev_queue_xmit() from their xmit function
(as some classifiers need skb->dst) : bonding, vlan, macvlan, eql, ifb, hdlc_fr
Signed-off-by: NEric Dumazet <dada1@cosmosbay.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      93f154b5
  25. 09 5月, 2009 1 次提交
  27. 17 4月, 2009 1 次提交
    • A
      wan/pc300_drv: convert to net_device_ops · d32da050
      由 Alexander Beregalov 提交于 
      On Fri, Apr 17, 2009 at 05:23:02AM +0400, Alexander Beregalov wrote:
>
> Signed-off-by: Alexander Beregalov <a.beregalov@gmail.com>
> ---
>  drivers/net/wan/pc300_drv.c |   22 ++++++++++++++--------
>  1 files changed, 14 insertions(+), 8 deletions(-)
>
> diff --git a/drivers/net/wan/pc300_drv.c b/drivers/net/wan/pc300_drv.c
> index c23fde0..df10a4c 100644
> --- a/drivers/net/wan/pc300_drv.c
> +++ b/drivers/net/wan/pc300_drv.c
> @@ -225,6 +225,7 @@ static char rcsid[] =
>  #include <linux/skbuff.h>
>  #include <linux/if_arp.h>
>  #include <linux/netdevice.h>
> +#include <linux/etherdevice.h>
>  #include <linux/spinlock.h>
>  #include <linux/if.h>
>  #include <net/arp.h>
> @@ -3246,6 +3247,18 @@ static inline void show_version(void)
>  		rcsvers, rcsdate, __DATE__, __TIME__);
>  }				/* show_version */
>
> +static const struct net_device_ops cpc_netdev_ops = {
> +	.ndo_init		= NULL,
> +	.ndo_open		= cpc_open,
> +	.ndo_stop		= cpc_close,
> +	.ndo_tx_timeout		= cpc_tx_timeout,
> +	.ndo_set_multicast_list	= NULL,

In this case ndo_init and ndo_set_multicast_list
are not needed.

>From 1507a5a797a5f0005696a9bf10e390caca9c3800 Mon Sep 17 00:00:00 2001
From: Alexander Beregalov <a.beregalov@gmail.com>
Date: Fri, 17 Apr 2009 05:45:48 +0400
Subject: [PATCH] wan/pc300_drv: convert to net_device_ops
Signed-off-by: NAlexander Beregalov <a.beregalov@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      d32da050
  29. 07 4月, 2009 2 次提交
  31. 30 3月, 2009 1 次提交
  33. 27 3月, 2009 1 次提交
  35. 22 3月, 2009 9 次提交
  37. 16 3月, 2009 1 次提交
    • J
      Rationalize fasync return values · 60aa4924
      由 Jonathan Corbet 提交于 
      Most fasync implementations do something like:

     return fasync_helper(...);

But fasync_helper() will return a positive value at times - a feature used
in at least one place.  Thus, a number of other drivers do:

     err = fasync_helper(...);
     if (err < 0)
             return err;
     return 0;

In the interests of consistency and more concise code, it makes sense to
map positive return values onto zero where ->fasync() is called.

Cc: Al Viro <viro@ZenIV.linux.org.uk>
Signed-off-by: NJonathan Corbet <corbet@lwn.net>
      60aa4924
  39. 10 3月, 2009 1 次提交
  41. 27 2月, 2009 2 次提交
  43. 18 2月, 2009 2 次提交
  45. 01 2月, 2009 1 次提交
  47. 22 1月, 2009 3 次提交